Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0504)
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | ResNet |
| Split | train |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 504 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8899 |
| Val Accuracy | 0.8413 |
| Test Accuracy | 0.8454 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pickup_truck, sweet_pepper, fox, dinosaur, beaver, shark, cockroach, hamster, lizard, oak_tree, motorcycle, caterpillar, camel, pear, elephant, dolphin, lobster, raccoon, whale, leopard, mushroom, ray, telephone, tulip, plain, keyboard, wardrobe, chimpanzee, rabbit, clock, baby, boy, tank, mouse, possum, skyscraper, tractor, spider, willow_tree, cloud, kangaroo, lamp, plate, wolf, sunflower, chair, train, rose, bowl, crab
- Downloads last month
- 34
Model tree for ProbeX/Model-J__ResNet__model_idx_0504
Base model
microsoft/resnet-101